# Aggregating explanation methods for stable and robust explainability

arXiv: https://arxiv.org/abs/1903.00519 · HTML: https://mlsanity.com/paper/1903.00519/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2019.

## Built on by (most cited first, 9 of 9)

- [Fooling Partial Dependence via Data Poisoning](https://mlsanity.com/paper/2105.12837/) (2021)
- [Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach](https://mlsanity.com/paper/2111.09121/) (2021)
- [Provably Better Explanations with Optimized Aggregation of Feature Attributions](https://mlsanity.com/paper/2406.05090/) (2024)
- [A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines](https://mlsanity.com/paper/2111.07379/) (2021)
- [Fidelity of Ensemble Aggregation for Saliency Map Explanations using Bayesian Optimization Techniques](https://mlsanity.com/paper/2207.01565/) (2022)
- [Aggregating Local Saliency Maps for Semi-Global Explainable Image Classification](https://mlsanity.com/paper/2506.23247/) (2025)
- [Uncertainty in Additive Feature Attribution methods](https://mlsanity.com/paper/2311.17446/) (2023)
- [Multi-criteria Rank-based Aggregation for Explainable AI](https://mlsanity.com/paper/2505.24612/) (2025)
- [XAI-Refine: An Automated Explanation-Knowledge Loop for Brain-Age Prediction](https://mlsanity.com/paper/2609.09388/) (2026)

## Abstract (arXiv)

Despite a growing literature on explaining neural networks, no consensus has been reached on how to explain a neural network decision or how to evaluate an explanation. Our contributions in this paper are twofold. First, we investigate schemes to combine explanation methods and reduce model uncertainty to obtain a single aggregated explanation. We provide evidence that the aggregation is better at identifying important features, than on individual methods. Adversarial attacks on explanations is a recent active research topic. As our second contribution, we present evidence that aggregate explanations are much more robust to attacks than individual explanation methods.